Skills/ClawHub/multi-role-tts-skill

multi-role-tts-skill@1.0.1

CAUTION· install only

Publisher claims: "Multi-role audio generator skill v1.0.1 全家桶版 - Universal professional tool for creating dialogue audio with multiple character voices." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher johnsun4414 · publishing for 234 daysInstalls 752Last detonated 19 min ago
What would fix thisWatchDispute verdict

Coverage

Install scripts ran; no agent task scenario for this bundle.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; install scripts ran; no agent task scenario for this bundle) on 2026-11-15 and scored it 78/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Privileged sudo command; Direct script execution from GitHub raw URL; Privileged sudo command. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocesssecond launch, clock +45 days, CI unset

Static findings

HIGH
Privileged sudo commandscripts/multirole-generator-final.sh:134 · Privileged sudo command — agent may execute with elevated privilegesecho -e " Ubuntu: sudo apt install ffmpeg"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actiontests/test_audio_concatenation.sh:76 · File type combined with upload action — agent may exfiltrate local data filesffmpeg -f concat -safe 0 -i concat_list.txt -c copy concat_output.mp3 2>/dev/nullFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File permission modification commandinstall.sh:215 · File permission modification command — agent changes file ownership/permissionssudo chmod +x "$target_dir/install.sh"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Direct script execution from GitHub raw URLinstall.sh:110 · Direct script execution from GitHub raw URL — unverified code source/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedgenerate-audio.py:82 · Python subprocess execution detectedresult = subprocess.run([Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Privileged sudo commandSKILL.md:291 · Privileged sudo command — agent may execute with elevated privileges# Ubuntu: sudo apt install ffmpegFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandinstall.sh:161 · Privileged sudo command — agent may execute with elevated privilegessudo yum install -y ffmpeg python3 python3-pipFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandinstall.sh:150 · Privileged sudo command — agent may execute with elevated privilegessudo apt install -y ffmpeg python3 python3-pipFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedgenerate-audio.py:114 · Python subprocess execution detectedresult = subprocess.run([Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Privileged sudo commandSKILL.md:63 · Privileged sudo command — agent may execute with elevated privilegessudo apt install ffmpegFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionpackage.json:7 · File type combined with upload action — agent may exfiltrate local data files"test": "./scripts/multirole-generator-final.sh --script examples/basic-dialogue.txt --output test-output.mp3",Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File permission modification commandinstall.sh:214 · File permission modification command — agent changes file ownership/permissionssudo chmod +x "$target_dir/scripts/"*.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File type combined with upload actionpackage.json:8 · File type combined with upload action — agent may exfiltrate local data files"example": "./scripts/multirole-generator-final.sh --script examples/service-dialogue.txt --output example-output.mp3",Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Privileged sudo commandinstall.sh:206 · Privileged sudo command — agent may execute with elevated privilegessudo mkdir -p "$target_dir"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandinstall.sh:147 · Privileged sudo command — agent may execute with elevated privilegessudo apt updateFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandinstall.sh:210 · Privileged sudo command — agent may execute with elevated privilegessudo cp -r ./* "$target_dir/"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈1,434 tok
1 file · 19 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim johnsun4414: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. Direct script execution from GitHub raw URL≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  4. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  5. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  6. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim johnsun4414Propose a patch to the maintainer